skip to main content

Title: Latency-Aware Dynamic Server and Cooling Capacity Provisioner for Data Centers
Data center operators generally overprovision IT and cooling capacities to address unexpected utilization increases that can violate service quality commitments. This results in energy wastage. To reduce this wastage, we introduce HCP (Holistic Capacity Provisioner), a service latency aware management system for dynamically provisioning the server and cooling capacity. Short-term load prediction is used to adjust the online server capacity to concentrate the workload onto the smallest possible set of online servers. Idling servers are completely turned off based on a separate long-term utilization predictor. HCP targets data centers that use chilled air cooling and varies the cooling provided commensurately, using adjustable aperture tiles and speed control of the blower fans in the air handler. An HCP prototype supporting a server heterogeneity is evaluated with real-world workload traces/requests and realizes up to 32% total energy savings while limiting the 99th-percentile and average latency increases to at most 6.67% and 3.24%, respectively, against a baseline system where all servers are kept online.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
SoCC '21, Seattle, WA
Page Range / eLocation ID:
335 to 349
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    With the rapid development of the Internet of Things (IoT), computational workloads are gradually moving toward the internet edge for low latency. Due to significant workload fluctuations, edge data centers built in distributed locations suffer from resource underutilization and requires capacity underprovisioning to avoid wasting capital investment. The workload fluctuations, however, also make edge data centers more suitable for battery-assisted power management to counter the performance impact due to underprovisioning. In particular, the workload fluctuations allow the battery to be frequently recharged and made available for temporary capacity boosts. But, using batteries can overload the data center cooling system which is designed with a matching capacity of the power system. In this paper, we design a novel power management solution, DeepPM, that exploits the UPS battery and cold air inside the edge data center as energy storage to boost the performance. DeepPM uses deep reinforcement learning (DRL) to learn the data center thermal behavior online in a model-free manner and uses it on-the-fly to determine power allocation for optimum latency performance without overheating the data center. Our evaluation shows that DeepPM can improve latency performance by more than 50% compared to a power capping baseline while the server inlet temperature remains within safe operating limits (e.g., 32°C). 
    more » « less
  2. Modern Information Technology (IT) servers are typically assumed to operate in quiescent conditions with almost zero static pressure differentials between inlet and exhaust. However, when operating in a data center containment system the IT equipment thermal status is a strong function of the non- homogenous environment of the air space, IT utilization workloads and the overall facility cooling system design. To implement a dynamic and interfaced cooling solution, the interdependencies of variabilities between the chassis, rack and room level must be determined. In this paper, the effect of positive as well as negative static pressure differential between inlet and outlet of servers on thermal performance, fan control schemes, the direction of air flow through the servers as well as fan energy consumption within a server is observed at the chassis level. In this study, a web server with internal air-flow paths segregated into two separate streams, each having dedicated fan/group of fans within the chassis, is operated over a range of static pressure differential across the server. Experiments were conducted to observe the steady-state temperatures of CPUs and fan power consumption. Furthermore, the server fan speed control scheme’s transient response to a typical peak in IT computational workload while operating at negative pressure differentials across the server is reported. The effects of the internal air flow paths within the chassis is studied through experimental testing and simulations for flow visualization. The results indicate that at higher positive differential pressures across the server, increasing server fans speeds will have minimal impact on the cooling of the system. On the contrary, at lower, negative differential pressure server fan power becomes strongly dependent on operating pressure differential. More importantly, it is shown that an imbalance of flow impedances in internal airflow paths and fan control logic can onset recirculation of exhaust air within the server. For accurate prediction of airflow in cases where negative pressure differential exists, this study proposes an extended fan performance curve instead of a regular fan performance curve to be applied as a fan boundary condition for Computational Fluid Dynamics simulations. 
    more » « less
  3. Over the past few years, there has been an ever increasing rise in energy consumption by IT equipment in Data Centers. Thus, the need to minimize the environmental impact of Data Centers by optimizing energy consumption and material use is increasing. In 2011, the Open Compute Project was started which was aimed at sharing specifications and best practices with the community for highly energy efficient and economical data centers. The first Open Compute Server was the ‘ Freedom’ Server. It was a vanity free design and was completely custom designed using minimum number of components and was deployed in a data center in Prineville, Oregon. Within the first few months of operation, considerable amount of energy and cost savings were observed. Since then, progressive generations of Open Compute servers have been introduced. Initially, the servers used for compute purposes mainly had a 2 socket architecture. In 2015, the Yosemite Open Compute Server was introduced which was suited for higher compute capacity. Yosemite has a system on a chip architecture having four CPUs per sled providing a significant improvement in performance per watt over the previous generations. This study mainly focuses on air flow optimization in Yosemite platform to improve its overall cooling performance. Commercially available CFD tools have made it possible to do the thermal modeling of these servers and predict their efficiency. A detailed server model is generated using a CFD tool and its optimization has been done to improve the air flow characteristics in the server. Thermal model of the improved design is compared to the existing design to show the impact of air flow optimization on flow rates and flow speeds which in turn affects CPU die temperatures and cooling power consumption and thus, impacting the overall cooling performance of the Yosemite platform. Emphasis is given on effective utilization of fans in the server as compared to the original design and improving air flow characteristics inside the server via improved ducting. 
    more » « less
  4. Modern day data centers are operated at high power for increased power density, maintenance, and cooling which covers almost 2 percent (70 billion kilowatt-hours) of the total energy consumption in the US. IT components and cooling system occupy the major portion of this energy consumption. Although data centers are designed to perform efficiently, cooling the high-density components is still a challenge. So, alternative methods to improve the cooling efficiency has become the drive to reduce the cooling cost. As liquid cooling is more efficient for high specific heat capacity, density, and thermal conductivity, hybrid cooling can offer the advantage of liquid cooling of high heat generating components in the traditional air-cooled servers. In this experiment, a 1U server is equipped with cold plate to cool the CPUs while the rest of the components are cooled by fans. In this study, predictive fan and pump failure analysis are performed which also helps to explore the options for redundancy and to reduce the cooling cost by improving cooling efficiency. Redundancy requires the knowledge of planned and unplanned system failures. As the main heat generating components are cooled by liquid, warm water cooling can be employed to observe the effects of raised inlet conditions in a hybrid cooled server with failure scenarios. The ASHRAE guidance class W4 for liquid cooling is chosen for our experiment to operate in a range from 25°C – 45°C. The experiments are conducted separately for the pump and fan failure scenarios. Computational load of idle, 10%, 30%, 50%, 70% and 98% are applied while powering only one pump and the miniature dry cooler fans are controlled externally to maintain constant inlet temperature of the coolant. As the rest of components such as DIMMs & PCH are cooled by air, maximum utilization for memory is applied while reducing the number fans in each case for fan failure scenario. The components temperatures and power consumption are recorded in each case for performance analysis 
    more » « less
  5. Adoption of renewable energy in power grids introduces stability challenges in regulating the operation frequency of the electricity grid. Thus, electrical grid operators call for provisioning of frequency regulation services from end-user customers, such as data centers, to help balance the power grid’s stability by dynamically adjusting their energy consumption based on the power grid’s need. As renewable energy adoption grows, the average reward price of frequency regulation services has become much higher than that of the electricity cost. Therefore, there is a great cost incentive for data centers to provide frequency regulation service. Many existing techniques modulating data center power result in significant performance slowdown or provide a low amount of frequency regulation provision. We present PowerMorph , a tight QoS-aware data center power-reshaping framework, which enables commodity servers to provide practical frequency regulation service. The key behind PowerMorph  is using “complementary workload” as an additional knob to modulate server power, which provides high provision capacity while satisfying tight QoS constraints of latency-critical workloads. We achieve up to 58% improvement to TCO under common conditions, and in certain cases can even completely eliminate the data center electricity bill and provide a net profit. 
    more » « less